output
20062026
most citedPathologies of Neural Models Make Interpretations Difficult

259 citations

Showing 2018Show all

5 papers · 1 filter

nucl-ex2018★ 15 cited

The structure of 70Fe: Single-particle and collective degrees of freedom

A. Gade, R. V. F. Janssens, J. A. Tostevin +16

Excited states in the neutron-rich \nuc{70}{Fe} nucleus were populated in a one-proton removal reaction from \nuc{71}{Co} projectiles at 87~MeV/nucleon. A new transition was observ…

math.AT2018

The realization problem for discrete Morse functions on trees

Yuqing Liu, Nicholas A. Scoville

We introduce a new notion of equivalence of discrete Morse functions on graphs called persistence equivalence. Two functions are considered persistence equivalent if and only if th…

physics.atom-ph2018★ 11 cited

Improving the state selectivity of field ionization with quantum control

Vincent C. Gregoric, Jason J. Bennett, Bianca R. Gualtieri +5

The electron signals from the field ionization of two closely-spaced Rydberg states of \mbox{rubidium-85} are separated using quantum control. In selective field ionization, the st…

cs.CL2018★ 259 cited

Pathologies of Neural Models Make Interpretations Difficult

Shi Feng, Eric Wallace, Alvin Grissom +3

One way to interpret neural model predictions is to highlight the most important input features---for example, a heatmap visualization over the words in an input sentence. In exist…

math.QA2018★ 2 cited

Combinatorial bases of principal subspaces of modules for twisted affine Lie algebras of type , , and

Marijana Butorac, Christopher Sadowski

We construct combinatorial bases of principal subspaces of standard modules of level with highest weight for the twisted affine Lie algebras of type $A_{2l-1}^{(2…